Traffic rescheduling system and method for generating traffic rescheduling proposals

Abstract

To provide a method which efficiently generates a lot of operation arrangement plans.SOLUTION: An operation arrangement system to produce operation arrangement plans comprises an arithmetic unit executing prescribed processes and a storage device able to be accessed by the arithmetic units. The arithmetic unit has a diagram prediction part to produce a prediction diagram, a state determination part for the arithmetic unit to determine whether any fake convergence state is included in the prediction diagram and a conglutination spot extraction part for the arithmetic unit to determine if a conglutination state is produced. The fake convergence state means that a conglutination spot is generated in the prediction diagram outputted by the diagram prediction part and a prediction diagram highly evaluated cannot be generated. The conglutination spot means an essential spot in an operation arrangement to solve the fake convergence state.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a timetable rescheduling system that efficiently generates many timetable rescheduling plans. [Background technology]

[0002] There is a train schedule rescheduling system that outputs train schedule rescheduling proposals.

[0003] The following prior art exists as background art in this technical field: Patent Document 1 (JP 2019-209797 A) describes an operation plan management system that includes a timetable replanning proposal creation system, a learning data generation unit that transmits learning data to the timetable replanning proposal creation system, and a traffic management unit that transmits timetable replanning schedule data to the timetable replanning proposal creation system and receives timetable replanning proposals, the timetable replanning action learning unit includes a simulation execution unit that receives the learning schedule data and outputs the suitability of the timetable change action, and a search rule update unit that creates search rules from the suitability, and the timetable replanning proposal search unit searches for timetable replanning proposals in accordance with the updated search rules and outputs them to the traffic management unit (see abstract). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2019-209797 Summary of the Invention [Problem to be solved by the invention]

[0005] The train rescheduling plans output by train rescheduling systems are sometimes erroneous or insufficient, necessitating training using sufficient training data. However, while train rescheduling due to minor train delays occurs frequently, major train delays due to operational disruptions are rare, making it difficult to collect sufficient training data (train rescheduling data) for training. Random generation methods that randomly generate train rescheduling plans are difficult to generate good plans, and the efficiency of generating training data is low. For this reason, it is desirable to identify key points in train rescheduling, efficiently increase the training data corresponding to these points, and then perform machine learning.

[0006] The present invention aims to realize a timetable rescheduling system that efficiently generates many timetable rescheduling plans. [Means for solving the problem]

[0007] A representative example of the invention disclosed in the present application is as follows: A timetable rescheduling system for generating timetable rescheduling proposals includes a calculation device that executes predetermined processing and a storage device accessible by the calculation device, the calculation device having a timetable prediction unit that generates a predicted timetable, a state determination unit that determines whether the predicted timetable includes a false convergence state, and a stalemate point extraction unit that determines whether a stalemate state has occurred, and the false convergence state is a state in which a stalemate point has occurred in the predicted timetable output by the timetable prediction unit, The indicators are at least one of the total delay time, the total delay time of express trains, the number of cancelled trains, the number of stations where cancelled trains stop, the total delay time for passengers, and the time until the schedule is restored. This is a state in which a predicted timetable cannot be generated, and the stuck point is a key point in rescheduling operations to resolve the false convergence state. [Effects of the Invention]

[0008] According to one aspect of the present invention, many timetable rescheduling plans can be generated efficiently. Objects, configurations, and advantages other than those described above will become apparent from the following description of the embodiments. [Brief explanation of the drawings]

[0009] [Figure 1]1 is a block diagram showing the logical configuration of a timetable rescheduling system according to an embodiment of the present invention. [Figure 2] FIG. 1 is a block diagram showing the physical configuration of a traffic rescheduling system according to an embodiment of the present invention. [Figure 3] FIG. 2 is a diagram illustrating an example of the configuration of planned timetable data according to the present embodiment. [Figure 4] FIG. 2 is a diagram illustrating an example of the configuration of feature amount data according to the present embodiment. [Figure 5] FIG. 2 is a diagram showing an example of the configuration of timetable adjustment data according to the present embodiment. [Figure 6] 1 is a flowchart of a process executed by the timetable rescheduling system of the present embodiment. [Figure 7] 10 is a flowchart of a stuck portion detection process according to the present embodiment. [Figure 8] 10 is a flowchart of a search weight determination process according to the present embodiment. [Figure 9] FIG. 10 is a diagram showing an example of a stuck point display screen in the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] First, an overview of the train timetable rescheduling system 100 according to an embodiment of the present invention will be described. The train timetable rescheduling system 100 according to this embodiment detects false convergence states and deadlocks during the generation of train timetable rescheduling plans and the operation of the timetable simulator (timetable evaluation and prediction unit 11). The user inputs a response to the deadlock, or by referring to past successful train timetable reschedulings, the system changes the weights used to generate perturbations so that the train timetable at the deadlocked point is more likely to be changed.

[0011] For example, when there is a relatively large delay, a false convergence state occurs when the timetable simulator repeatedly performs calculations but is unable to generate a rescheduling plan to resolve the impasse, or when delays increase only for trains near the impasse. In other words, a false convergence state occurs when a stalemate occurs within a specific range (time or station) in the predicted timetable output by the timetable simulator, making it impossible to generate a predicted timetable that further reduces the KPI. A stalemate is also a state in which a certain train at a certain station needs to be rescheduled, that is, a point that is a key point (bottleneck) for resolving the false convergence state.

[0012] FIG. 1 is a block diagram showing the logical configuration of a timetable rescheduling system 100 according to this embodiment.

[0013] The train timetable rescheduling system 100 of this embodiment has a timetable evaluation and prediction unit 11, an inference unit 12, a perturbation generation unit 13, a state determination unit 14, a stalemate extraction unit 15, a display unit 16, a factor estimation unit 17, a weight determination unit 18, and a data recording unit 19.

[0014] FIG. 2 is a block diagram showing the physical configuration of the timetable rescheduling system 100 of this embodiment.

[0015] The timetable rescheduling system 100 of this embodiment is configured by a computer having a processing unit 110, a storage device 120, an input / output interface 130, and a communication interface 140.

[0016] The processing unit 110 is an arithmetic device having a processor (CPU) and memory. The processor executes programs stored in the memory. The processor executes various programs (e.g., a timetable evaluation and prediction program 111, a timetable rescheduling learning and proposal program 112, a perturbation generation program 113, a state determination program 114, a stalemate extraction program 115, a factor estimation program 117, a weight determination program 118, etc.), thereby realizing the functions of each unit of the timetable rescheduling system 100 (e.g., the timetable evaluation and prediction unit 11, the inference unit 12, the perturbation generation unit 13, the state determination unit 14, the stalemate extraction unit 15, the display unit 16, the factor estimation unit 17, the weight determination unit 18, the data recording unit 19, etc.). Note that some of the processing performed by the processor executing the programs may be executed by another arithmetic device (e.g., hardware such as an ASIC or FPGA).

[0017] Memory includes ROM, which is a non-volatile storage element, and RAM, which is a volatile storage element. ROM stores unchanging programs (e.g., BIOS). RAM is a high-speed, volatile storage element such as DRAM (Dynamic Random Access Memory), and temporarily stores programs executed by a processor and data used during program execution.

[0018] The storage device 120 is, for example, a large-capacity, non-volatile storage device such as a magnetic storage device (HDD) or a flash memory (SSD). The storage device 120 also stores data used by the processor when executing the program (e.g., planned timetable data 121, predicted timetable data 122, feature data 123, timetable rescheduling data 124, success case data 125, etc.), and the program executed by the processor. That is, the program is read from the storage device 120, loaded into memory, and executed by the processor to realize each function of the timetable rescheduling system 100.

[0019] The input / output interface 130 is an interface to which an input device 160 such as a keyboard or a mouse and an output device 170 such as a display device or a printer (not shown) are connected, and which receives input from a user and outputs the results of program execution in a format that can be viewed by the user. Note that a user terminal connected to the timetable replanning system 100 via a network may provide the input device 160 and the output device 170. In this case, the timetable replanning system 100 may have the functionality of a web server, and the user terminal may access the timetable replanning system 100 using a predetermined protocol (for example, http).

[0020] The communication interface 140 is a network interface device that controls communication with other devices according to a predetermined protocol.

[0021] The program executed by the processor is provided to the timetable replanning system 100 via removable media (CD-ROM, flash memory, etc.) or a network, and is stored in a non-volatile storage device 120, which is a non-transitory storage medium. For this reason, the timetable replanning system 100 should preferably have an interface for reading data from removable media.

[0022] The traffic rescheduling system 100 is a computer system configured on a single physical computer or on multiple logically or physically configured computers, and may operate on a virtual computer constructed on multiple physical computer resources. For example, the timetable evaluation and prediction unit 11, the inference unit 12, the perturbation generation unit 13, the state determination unit 14, the stalemate extraction unit 15, the display unit 16, the factor estimation unit 17, the weight determination unit 18, and the data recording unit 19 may each operate on separate physical or logical computers, or multiple units may be combined to operate on a single physical or logical computer.

[0023] Next, the functions and operations of each functional unit and program will be described.

[0024] The timetable evaluation and prediction unit 11 is a timetable simulator that generates a predicted timetable based on planned timetable data 121, the details of the failure, perturbations, and deadlock points by executing a timetable evaluation and prediction program 111. The generated predicted timetable is stored in predicted timetable data 122. The timetable evaluation and prediction unit 11 also calculates KPIs, which are evaluation indices for the generated predicted timetable. KPIs can be used as total delay time, total delay time of express trains and other high-speed trains, number of canceled trains, number of stations where canceled trains stop, total delay time for users, time until the timetable is restored, etc., and a predicted timetable with a low KPI can be said to be more convenient for users.

[0025] The inference unit 12 executes the timetable rescheduling learning and proposal program 112 to calculate timetable rescheduling proposals using the initial values ​​of the predicted timetable.

[0026] The perturbation generation unit 13 generates a perturbation by executing the perturbation generation program 113, and generates a timetable replanning plan by adding the generated perturbation.

[0027] The state determination unit 14 determines whether the predicted timetable includes a false convergence state by executing the state determination program 114. As described above, a false convergence state is a state in which a stalemate occurs in a specific range (time or station) in the predicted timetable output by the timetable simulator (timetable evaluation and prediction unit 11), and a predicted timetable that further reduces the KPI cannot be generated.

[0028] The stalemate extraction unit 15 executes the stalemate extraction program 115 to determine whether a stalemate has occurred for each train and station. As described above, a stalemate is a point at a station where a train's traffic rescheduling is necessary, i.e., a point that is a key point (bottleneck) for resolving a false convergence state. For example, a stalemate is determined to have occurred when delays are greater than those in the surrounding area within a specific range (time or station), delays increase after a specific point (time or station) (the train is at the forefront of the delay), there is a contradiction that makes it impossible to realize the stalemate (e.g., an overtaking at a station without a siding), an express train (e.g., a limited express train, a paid express train, etc.) is involved, or the impact of a timetable adjustment on future times is significant (e.g., tracing the time after the stalemate point reveals increasing delays and malfunctions, significantly affecting subsequent trains). Details of the processing by the stalemate extraction unit 15 will be described with reference to FIG. 7.

[0029] The display unit 16 is an interface that displays a stuck point display screen 900 (FIG. 9) and receives input from the operator.

[0030] The factor estimation unit 17 executes the factor estimation program 117 to estimate the cause of the detected deadlock.

[0031] The weight determination unit 18 determines search weights in accordance with the estimated cause of the stalemate by executing the weight determination program 118. Details of the processing by the weight determination unit 18 will be described with reference to FIG.

[0032] The data recording unit 19 stores the traffic rescheduling data with a low KPI in the success case data 125.

[0033] Planned timetable data 121 is data on planned train operating times, and details thereof will be explained with reference to FIG. 3. Predicted timetable data 122 is data on operating times predicted from actual train operating times. Feature amount data 123 is data indicating the characteristics of the amount of adjustment to the train timetable, and is output by the timetable evaluation and prediction unit 11. Details of the feature amount data 123 will be explained with reference to FIG. 4. Train rescheduling data 124 is data on train rescheduling candidates inferred by the inference unit 12, and details thereof will be explained with reference to FIG. 5. Success case data 125 is data in which KPIs were good as a result of train rescheduling.

[0034] FIG. 3 is a diagram showing an example of the configuration of the planned schedule data 121.

[0035] The planned timetable data 121 is data in which the train ID, which is unique identification information for the train, the train's departure station, the train's destination, the train type (local train or express train), station ID, which is identification information for multiple stations where the train stops or passes, the arrival and departure platform numbers of the stations, and the arrival and departure times are recorded for each train and station. Note that the predicted timetable data 122 may also be in the same format as the planned timetable data 121.

[0036] FIG. 4 is a diagram showing an example of the configuration of the feature amount data 123.

[0037] The feature data 123 is data indicating the characteristics of train schedule revisions, and is data in which the train ID, station ID, platform number which is identification information for the platform where the train departs and arrives, destination, and delay time which is the difference between the predicted schedule and the planned schedule are recorded for each train and station. In addition to the data shown in the figure, the feature data 123 may also include train type. The feature data 123 may also include information on the disruption that caused the train delay. The disruption information may include data on the train where the disruption occurred, the station (or section) where the disruption occurred, the direction of travel of the disrupted train, the time of the disruption, and the time of resumption.

[0038] FIG. 5 is a diagram showing an example of the configuration of the timetable adjustment data 124.

[0039] The traffic rescheduling data 124 is data in which the train ID, station ID, and traffic rescheduling details are recorded for each train. The traffic rescheduling details include changes in arrival and departure order and platform changes as shown in the figure, as well as partial service suspension and operational cutoff. In addition to the data shown in the figure, the traffic rescheduling data 124 may also include the time required for traffic rescheduling and the platform on which the traffic rescheduling will occur.

[0040] FIG. 6 is a flowchart of the process executed by the timetable rescheduling system 100.

[0041] First, fault information input from the input / output interface 130 or the communication interface 140 is received (1001).

[0042] Next, the timetable evaluation and prediction unit 11 applies the inputted fault information to the planned timetable data 121 and calculates the initial value of the predicted timetable (1002).

[0043] Next, the inference unit 12 calculates a timetable rescheduling plan using the initial values ​​of the predicted timetable (1003).

[0044] Next, the perturbation generation unit 13 generates a perturbation and generates a timetable replanning plan by adding the generated perturbation, for example, by randomly changing the content of the timetable replanning and parameters (delay time, arrival / departure platform, etc.).

[0045] Next, the timetable evaluation and prediction unit 11 applies the generated timetable adjustment plan to the initial predicted timetable to calculate predicted timetable data 122 (1005).

[0046] Next, the state determination unit 14 determines whether the calculated predicted timetable data 122 includes a false convergence state (1006). For example, if the decrease in the KPI of the predicted timetable, which is repeatedly calculated in the loop between the timetable evaluation / prediction unit 11 and the state determination unit 14, from the KPI of the previous predicted timetable is smaller than a predetermined threshold (i.e., the KPI of the predicted timetable has increased from the KPI of the previous predicted timetable or the decrease from the previous time is smaller than a predetermined threshold), and the predicted timetable has converged, if the KPI is larger than the predetermined threshold, it is determined that the KPI is in a false convergence state. If it is determined that the predicted timetable data 122 includes a false convergence state as a result, the stalemate point extraction unit 15 extracts a stalemate point from the predicted timetable data 122 (1007). Details of the stalemate point extraction process will be described with reference to FIG. 7.

[0047] Next, the display unit 16 outputs display data for displaying the stuck point display screen (FIG. 9) and prompts the operator to select a response.

[0048] Next, the cause estimation unit 17 estimates the cause of the detected stalemate based on whether it matches a predetermined stalemate pattern (1009).

[0049] Next, the weight determination unit 18 determines search weights according to the causes of the stalemate estimated by the cause estimation unit 17 (1010), and the process returns to step 1003 to create the next timetable rescheduling plan. Details of the search weight determination process will be explained with reference to FIG. 8. The determined search weights are used by the perturbation generation unit 13 to generate perturbations. By increasing the weights of the parts that cause the stalemate, many timetable rescheduling plans that resolve the causes of the stalemate are created.

[0050] The factor estimation unit 17 estimates the stalemate factor and the weight determination unit 18 determines the search weight in the following patterns, for example. (1) There is a pattern in which the departure order cannot be changed because there are trains waiting to overtake the delayed train, and the impact on the waiting train and the following trains increases. In this case, the departure order of the train in question is changed, and the order change is also effective for the following trains, and the weight determination unit 18 determines the weight that will result in the most changes in departure order. (2) There is a pattern in which a train cannot enter a station because the scheduled arrival / departure platform is not available, which increases the delay of the following train. In this case, changing the arrival / departure platform at the station is effective, and the weight determination unit 18 determines the weight that results in the most changes to the arrival / departure platform. (3) There are cases where trains should be partially suspended on the section where the failure occurred and should be turned around before that point, but there is no suitable subsequent operation for the turnaround train. In this case, the weight determination unit 18 determines a weight that will result in more operations after the partial suspension. (4) There are patterns in which many factors are involved and it is difficult to determine the main factor. In such cases, the weight determination unit 18 determines a weight that generates many possible reschedulings for the train and time. (5) If the stalemate point cannot be identified, the weight determining unit 18 determines the weight so that a perturbation occurs overall, without weighting a specific traffic rescheduling method.

[0051] On the other hand, if it is determined in step 1006 that the predicted timetable data 122 does not contain a false convergence state, the timetable evaluation and prediction unit 11 determines whether the KPI has decreased in this predicted timetable data 122 (1011). As described above, KPIs include the total delay time, the total delay time of express trains and other high-speed trains, the number of canceled trains, the number of stations where canceled trains stop, the total delay time for users, and the time until the timetable is restored. As a result, if the KPI has decreased, the timetable rescheduling data for the relevant timetable rescheduling plan is sent to the data recording unit 19 and recorded in the success case data 125 (1012). On the other hand, if the KPI has not decreased, the process returns to step 1003 and another timetable rescheduling plan is calculated.

[0052] FIG. 7 is a flowchart of the stuck point detection process.

[0053] Specifically, the stalemate point extraction unit 15 determines, for each train and station in the predicted timetable data 122, whether delays are concentrated in a specific area near the train and station (1022), whether the train and station are at the forefront of the delay (1023), whether a contradiction has occurred at the train and station (1024), and whether an express train is involved (1025). If none of the conditions are met, the train and station are determined not to be a stalemate point (1026). On the other hand, if any one of the conditions is met, the train and station are determined to be a stalemate point (1027). After determining whether all train and station combinations are stalemate points, the stalemate point detection process is terminated and the process returns to the calling process.

[0054] FIG. 8 is a flowchart of the search weight determination process.

[0055] First, the weight determination unit 18 determines whether or not a corresponding input has been made to the stuck point display screen 900 (FIG. 9) for each stuck point (1032).

[0056] If there is a corresponding input, the weight determination unit 18 sets a large weight (for example, to the maximum) for the sorting content that matches the input content so that many perturbations related to the input content occur (1033). Note that, without determining whether there is a corresponding input in step 1032, past similar states may be automatically searched for in step 1034.

[0057] On the other hand, if there is no corresponding input (if "No operation" is selected on the stalemate point display screen 900 in Figure 9), the weight determination unit 18 searches for similar past stalemate states from the success case data 125 (1034), and sets a large weight (for example, to the maximum) for the reorganization procedure that matches the reorganization content in the similar past stalemate state, so that many perturbations related to the searched reorganization procedure occur (1035).

[0058] After that, the weight determination unit 18 determines search weights for all stuck points, and then ends the search weight determination process and returns to the process that called it.

[0059] FIG. 9 is a diagram showing an example of a stuck point display screen 900.

[0060] The stuck point display screen 900 includes a diamond display area 910, a stuck point display area 920, and a corresponding selection input area 930.

[0061] The timetable display area 910 displays a graph of the train timetable with the horizontal axis representing time and the vertical axis representing station (distance from the starting station of the line), and superimposes detected stall points on the train timetable. The stall display area 920 displays information about the detected stall points. The response selection input area 930 displays proposed responses to the detected stall points, and any of them can be selected. If multiple stall points are detected, a response can be selected for each detected stall point. If it is not determined whether a response has been input in step 1032 of the search weight determination process, the response selection input area 930 does not need to be displayed.

[0062] Although the embodiment of the present invention has been described above using a railway timetable as an example, the present invention can also be applied to simulators of passenger and freight transport schedules.

[0063] The present invention is not limited to the above-described embodiments, but includes various modifications and equivalent configurations within the spirit and scope of the appended claims. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to configurations including all of the described configurations. Furthermore, part of the configuration of one embodiment may be replaced with the configuration of another embodiment. Furthermore, the configuration of another embodiment may be added to the configuration of one embodiment. Furthermore, part of the configuration of each embodiment may be added, deleted, or replaced with other configurations.

[0064] Furthermore, the aforementioned configurations, functions, processing units, processing means, etc. may be realized in part or in whole in hardware, for example by designing them as integrated circuits, or may be realized in software by a processor interpreting and executing a program that realizes each function.

[0065] Information such as programs, tables, and files that realize each function can be stored in a storage device such as a memory, a hard disk, or an SSD (Solid State Drive), or in a recording medium such as an IC card, an SD card, or a DVD.

[0066] In addition, the control lines and information lines shown are those that are considered necessary for the explanation, and do not necessarily show all the control lines and information lines that are necessary for implementation. In reality, it can be considered that almost all components are interconnected. [Explanation of symbols]

[0067] 11 Prediction Department 12 Reasoning part 13 Perturbation generator 14 Status determination unit 15 Extraction of stuck areas 16 Display section 17 Factor estimation section 18 Weight determination unit 19 Data recording section 100 Train rescheduling system 110 Processing section 111 Prediction Program 112 Proposed Program 113 Status Judgment Program 114 Stalemate Extraction Program 115 Factor Estimation Program 116 Weight Determination Program 117 Perturbation Generator 120 Storage device 121 Planned timetable data 122 Predicted timetable data 123 Feature Data 124 Train rescheduling data 125 Success Case Data 130 Input / Output Interface 140 Communication Interface 160 Input Devices 170 Output Device 900 Stalemate display screen

Claims

1. A traffic rescheduling system that generates a traffic rescheduling plan, A computing device that executes predetermined processing and a storage device that can be accessed by the computing device, The calculation device includes a timetable prediction unit that generates a predicted timetable; a state determination unit that determines whether the predicted timetable includes a false convergence state; the computing device has a stalemate location extraction unit that determines whether a stalemate has occurred, The false convergence state is a state in which a stalemate occurs in the predicted timetable output by the timetable prediction unit, and a predicted timetable with a small index cannot be generated using at least one of the indexes: the total delay time, the total delay time of express trains, the number of canceled trains, the number of stations where the canceled trains stop, the total delay time for users, and the time until the timetable is restored; A traffic rescheduling system characterized in that the stalemate point is a key point in traffic rescheduling to resolve the false convergence state.

2. The traffic rescheduling system according to claim 1, The state determination unit determines that a false convergence state is present if the decrease in the index of the predicted timetable repeatedly generated by the timetable prediction unit from the index of the previously generated predicted timetable is smaller than a predetermined threshold, or if the index is larger than a predetermined threshold.

3. The traffic rescheduling system according to claim 1, The traffic rescheduling system is characterized in that the stalemate extraction unit determines that a stalemate exists when at least one of the following conditions is met: delays are concentrated in a specific range of trains and stations; the train and station are at the forefront of the delay; a contradiction has occurred between the train and station; and an express train is involved.

4. The traffic rescheduling system according to claim 1, the calculation device has a factor estimation unit that estimates a factor of the determined stalemate; a perturbation generation unit configured to generate a perturbation and generate a timetable replanning plan by adding the generated perturbation; the calculation device has a weight determination unit that determines a search weight in accordance with the estimated cause of the deadlock; The perturbation generation unit generates a perturbation by changing the points reflected in the timetable according to the determined weight.

5. The traffic rescheduling system according to claim 4, A traffic rescheduling system characterized in that the weight determination unit sets a large weight for a rescheduling procedure that matches the rescheduling content in a similar stalemate in the past.

6. The traffic rescheduling system according to claim 4, the factor estimation unit estimates a factor of the stalemate based on whether the factor matches a predetermined stalemate pattern; A timetable rescheduling system characterized in that the weight determination unit determines a weight that generates more perturbations at the location of the estimated cause of the deadlock.

7. The traffic rescheduling system according to claim 1, A train schedule rescheduling system characterized by comprising a display unit that outputs display data for superimposing and displaying stalemate areas on the predicted timetable.

8. A method for generating a timetable replanning plan executed by a timetable replanning system, comprising: The timetable rescheduling system has a calculation device that executes predetermined processing and a storage device that can be accessed by the calculation device, The method for generating a timetable rescheduling plan comprises: a timetable prediction procedure in which the calculation device generates a predicted timetable; a state determination step in which the calculation device determines whether the predicted timetable includes a false convergence state; a stalemate point extraction procedure for determining whether a stalemate state has occurred, The false convergence state is a state in which a stalemate occurs in the predicted timetable output by the timetable prediction procedure, and a predicted timetable with a small index cannot be generated using at least one of the indexes: total delay time, total delay time of express trains, number of canceled trains, number of stations where canceled trains stop, total delay time for users, and time until the timetable is restored; A method for generating timetable replanning proposals, characterized in that the stalemate point is a key point in timetable replanning to resolve the false convergence state.

Images